• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.31-38
• /
• 2023

This paper introduces a real-time face swapping system that enables video influencers to swap their faces with arbitrary generated face images of their choice. The system is implemented as a Django-based server that uses a REST request to communicate with the generative model,specifically the pretrained stable diffusion model. Once generated, the generated image is displayed on the front page so that the influencer can decide whether to use the generated face or not, by clicking on the accept button on the front page. If they choose to use it, both their face and the generated face are sent to the landmark extraction module to extract the landmarks, which are then used to swap the faces. To minimize the fluctuation of landmarks over time that can cause instability or jitter in the output, a temporal filtering step is added. Furthermore, to increase the processing speed the system works on a reduced set of the extracted landmarks.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.535-546
• /
• 2019

Recently, there have been a lot of researches on the whole face replacement system, but it is not easy to obtain stable results due to various attitudes, angles and facial diversity. To produce a natural synthesis result when replacing the face shown in the video image, technologies such as face area detection, feature extraction, face alignment, face area segmentation, 3D attitude adjustment and facial transposition should all operate at a precise level. And each technology must be able to be interdependently combined. The results of our analysis show that the difficulty of implementing the technology and contribution to the system in facial replacement technology has increased in facial feature point extraction and facial alignment technology. On the other hand, the difficulty of the facial transposition technique and the three-dimensional posture adjustment technique were low, but showed the need for development. In this paper, we propose four facial replacement models such as 2-D Faceswap, OpenPose, Deekfake, and Cycle GAN, which are suitable for the Cox platform. These models have the following features; i.e. these models include a suitable model for front face pose image conversion, face pose image with active body movement, and face movement with right and left side by 15 degrees, Generative Adversarial Network.

• Journal of Korean Ophthalmic Optics Society
• /
• v.20 no.2
• /
• pp.167-175
• /
• 2015

Purpose: The new-type rangefinder, which is using the biprism principle, is introduced to develop the range finder which can be easily carried by soldiers, and in order to realize those technologies specifically, we try to develop a scope for military rangefinder by doing optical design which can secure enough space to move the biprism. Methods: After setting up the verious initial condition to realize two kinds of goals, that are the securement of enough space to move the biprism and the easy-exchangeability of two kinds of biprisms, and then the optical system was optimized by using optical design program CodeV in order to minimize the finite ray aberrations. Results: We designed the biprism housing to makes it possible to swap the two kinds of biprisms. It was appeared that the Schmidt prism is suitable as erecting prism which can make sure the space to move the biprism. 16.5 mm was good for the face length of Schmidt prism. The optical system with a Schmidt prism and a biprism was designed, and the finite ray aberrations was minimized. Conclusions: We developed a 5X scope for an optical rangefinder using a biprism and a Schmidt prism with 16.5 mm face length. This scope is valid for the optical system which has the effective field angle of ${\pm}3.6^{\circ}$, and the finite ray aberrations are well controlled within the ${\pm}8.95^{\prime}$.